Multi-Server Backup Synchronization via I/O Handler Coordination

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing data protection systems face challenges in synchronizing data across multiple servers without application awareness, leading to inefficiencies and potential data corruption, especially in distributed environments where applications span multiple volumes and servers.

Innovation Solution

A method and system that utilize I/O Handlers to initiate coordinated backup operations across multiple servers by calculating a time value based on communication latency and clock differences, allowing for synchronized data protection without requiring application integration or downtime, using a Time Synchronizer Server and I/O Handlers to stretch or freeze I/O operations for consistent snapshots.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If hardware snapshotting is used to protect data across multiple servers, then data protection capability is improved, but application awareness and synchronization consistency deteriorate because hardware solutions are unaware of application affinity

Engineering Contradiction:
Improvedata protection capabilityVSAvoidapplication synchronization consistency
Core Design Contradiction:
ReliabilityVSLoss of information

Solution Approach 1:

The patent introduces a consistency group manager as an intermediary layer between hardware snapshotting and applications. This manager coordinates snapshots across multiple servers and volumes, ensuring application-level consistency without requiring direct application involvement. The consistency group manager tracks application affinity and orchestrates synchronized snapshots across distributed servers, resolving the contradiction between hardware-level protection and application-level consistency.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent changes the coordination parameter from hardware-level timing to application-aware timing by introducing consistency groups. Each consistency group represents a logical unit of application data spanning multiple servers, and snapshots are coordinated based on these groups rather than individual hardware volumes. This parameter change enables consistent data protection across distributed servers while maintaining application affinity awareness.

Inventive Principle:
Principle #35Parameter changes

2Loss of information

If software snapshotting is used with additional synchronization, then application consistency is improved, but system complexity and operation overhead worsen

Engineering Contradiction:
Improveapplication consistencyVSAvoidsynchronization system complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The consistency group manager serves multiple functions: it tracks application affinity, coordinates snapshots across servers, manages consistency groups, and orchestrates recovery operations. By consolidating these functions into a single universal manager rather than implementing separate synchronization mechanisms for each application, the system achieves application consistency without proportionally increasing complexity.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system enables applications to be protected without requiring application-awareness or direct application involvement. The consistency group manager automatically discovers and tracks application data across servers, and snapshots are taken without requiring application participation. This self-service approach maintains consistency while minimizing operational overhead.

Inventive Principle:
Principle #25Self-service

3Reliability

If traditional backup methods are used across multiple servers, then data protection coverage is improved, but downtime and application disruption worsen

Engineering Contradiction:
Improvedata protection coverageVSAvoidapplication downtime
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-establishing consistency groups and tracking application data relationships before backups are needed. When a snapshot is required, the coordination is already in place, allowing immediate execution without application disruption. The consistency group manager maintains ready-state knowledge of data locations and relationships, enabling rapid snapshot execution.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent enables continuous data protection by making snapshots transparent to applications. Applications continue to operate without interruption while snapshots are taken in the background. The consistency group manager coordinates snapshots during normal operation, ensuring that data protection occurs continuously without requiring application downtime or disruption.

Inventive Principle:
Principle #20Continuity of useful action

4Loss of information

If I/O operations are frozen during backup to ensure consistency, then data consistency is improved, but productivity and system performance worsen

Engineering Contradiction:
Improvedata consistencyVSAvoidsystem performance
Core Design Contradiction:
Loss of informationVSProductivity

Solution Approach 1:

The I/O handler acts as an intermediary between applications and storage operations during snapshots. Instead of freezing all I/O operations, the I/O handler selectively manages I/O requests related to the consistency group being snapshotted. This allows unrelated I/O operations to continue normally, maintaining system performance while ensuring consistency for the specific data being protected.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent applies consistency enforcement locally to specific consistency groups rather than globally across all I/O operations. Each consistency group is snapshotted independently, and I/O management is applied only to the relevant data. This local approach ensures data consistency for protected applications while allowing other system operations to proceed without performance degradation.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP2366150B1Method and system for multi-server application synchronization without stopping I/O
Publication Date: 2012.09.05 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • EP2366150B1 patent drawingFigure 1
  • EP2366150B1 patent drawingFigure 2
  • EP2366150B1 patent drawing

AI summary

A method according to one embodiment includes receiving a request to perform a backup of data associated with an application running on multiple servers; calculating a time value based on communications with the servers, the time value calculation including at least one of a latency of at least one of the communications, and a difference between a reference time clock value and a time clock value of at least one of the servers; and communicating with I/O Handlers on the servers for initiating a coordinated backup operation on the data at about a same start time. Additional systems, methods, and computer program products are also disclosed.